一种新的基于归一化峭度的ICA算法  

A New ICA Algorithm Based on Normalized Kurtosis

作　　者：崔志涛[1] 温洁嫦[1] 胡南辉[1] 

机构地区：[1]广东工业大学应用数学学院,广东广州510006

出　　处：《广东工业大学学报》2007年第4期38-41,共4页Journal of Guangdong University of Technology

摘　　要：基于峭度的独立分量分析中,采用梯度法寻找代价函数的极值点时,搜索的方向对算法的收敛起着关键的作用,对Kuicnet算法中原来的梯度做一个倍数替换,得到一个新的ICA算法.新算法在迭代过程中适时对梯度方向作出调整,加快收敛速度.数值仿真说明了算法的有效性.The traditional approach to gradient to search for the cost function＇ s extreme in the independent component analysis was based on kurtosis. The path we are looking for is crucial to the convergence of the algorithm. In the Kuicnet algorithm, after replacing the gradient of the cost function with its scaling we obtained a new ICA algorithm. Adjusting the path of the gradient timely in the iterative process, it accelerates the convergence. The simulation illustrates the effectiveness.

关 键 词：独立分量分析 峭度 快速ICA算法 

分 类 号：TN911[电子电信—通信与信息系统]